{"id":"CVE-2024-4181","details":"A command injection vulnerability exists in the RunGptLLM class of the llama_index library, version 0.9.47, used by the RunGpt framework from JinaAI to connect to Language Learning Models (LLMs). The vulnerability arises from the improper use of the eval function, allowing a malicious or compromised LLM hosting provider to execute arbitrary commands on the client's machine. This issue was fixed in version 0.10.13. The exploitation of this vulnerability could lead to a hosting provider gaining full control over client machines.","aliases":["GHSA-pw38-xv9x-h8ch"],"modified":"2026-03-14T12:36:06.567702Z","published":"2024-05-16T09:15:15.553Z","references":[{"type":"FIX","url":"https://github.com/run-llama/llama_index/commit/d73715eaf0642705583e7897c78b9c8dd2d3a7ba"},{"type":"EVIDENCE","url":"https://huntr.com/bounties/1a204520-598a-434e-b13d-0d34f2a5ddc1"}],"affected":[{"ranges":[{"type":"GIT","repo":"https://github.com/run-llama/llama_index","events":[{"introduced":"f8893ad2656036a58ea2284ec6cc2b3bc5a83283"},{"fixed":"6d642a0893aced9bed026c5c15e17c41575ca024"},{"fixed":"d73715eaf0642705583e7897c78b9c8dd2d3a7ba"}],"database_specific":{"versions":[{"introduced":"0.9.47"},{"fixed":"0.10.13"}]}}],"database_specific":{"source":"https://storage.googleapis.com/cve-osv-conversion/osv-output/CVE-2024-4181.json"}}],"schema_version":"1.7.5","severity":[{"type":"CVSS_V3","score":"CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H"}]}